Rutherford, Alex Center for Humans and Machines, Max Planck Institute for Human Development, Max Planck Society;
https://doi.org/10.1371/journal.pone.0272168 (Verlagsversion)
https://figshare.com/articles/figure/Predictive_functions_/20420088 (Ergänzendes Material)
https://figshare.com/articles/figure/Sigmoid_function_calculating_rain_probability_/20420091 (Ergänzendes Material)
https://figshare.com/articles/figure/Prediction_error_by_algorithmic_players_/20420094 (Ergänzendes Material)
https://figshare.com/articles/figure/Histogram_of_predictions_/20420097 (Ergänzendes Material)
https://figshare.com/articles/journal_contribution/Supplementary_tables_/20420100 (Ergänzendes Material)
https://osf.io/t38z9/ (Forschungsdaten)
journal.pone.0272168.pdf (Verlagsversion), 2MB
Pescetelli, N., Reichert, P., & Rutherford, A. (2022). A variational-autoencoder approach to solve the hidden profile task in hybrid human-machine teams. PLoS ONE, 17(8): e0272168. doi:10.1371/journal.pone.0272168.
